Training in progress, step 3

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "facebook/blenderbot_small-90M",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BlenderbotSmallForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 8,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 8,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "xlm",
+  "length_penalty": null,
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "min_length": null,
+  "model_type": "blenderbot-small",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 54944
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb79775444fe54fbf69f4714587c1bcdc3406858723e0a1a75a4bbd5935c6c99
+size 350295176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d029cd125d787ab4e4e879aaa05e2a43e20eb75d95eba58b4861bff0ebf74e20
+size 5240